Hi everyone!
Welcome to the fourth edition of my EPL Predictions newsletter, where each week, I'll post detailed forecasts for each game.
As a general rule of thumb, each issue will contain an assessment of the previous week's forecasts, plus naive and biased predictions for upcoming games.
(you can learn more about the general assumptions of the model here)
Let's get to it.
End-of-season predictions
After a predictable gameweek, most of my model's projections remain the same, with Liverpool increasing their chances of a title slightly (by 2 percentage points vs. the previous simulation).
On the other end of the table, Southampton & Aston Villa keep pulling toward the relegation zone.
Naive Predictions
The naive predictions are computed using historical data only, and it's the forecast system that I use to simulate the end-of-season probabilities for the Premier League.
The following table showcases each game's forecasts under this model.
Biased Predictions
In this section, I present my biased forecasts, which, are based on both my hunch and historical data. For each match, I'll present a detailed viz with probabilities for different events within the match and a small write-up.
The following table shows the summary of my biased forecasts.
On my exact scoreline predictions from last week, I got six correct results and two exact scoreline predictions by nailing the forecast on the Arsenal and West Ham games.
Fulham vs. Brighton & Hove Albion
You could argue that Fulham were unlucky not to get out with a point from the game against Arsenal, and I think they're proving they have what it takes to be in the Premier League next season.
Potter, has been doing a massive job at Brighton for some time, and I think we're finally seeing it bear fruit. I wouldn't go as far as to say that the Seagulls could get Champions League football next season, but Europa, why not?
I think this one will end in a draw, with a goal for both sides.
Crystal Palace vs. Brentford
I might have overestimated Brentford, and although they're still a pretty solid side, I'm guessing that they'll still find it pretty hard to get away with a point in games like these.
Palace have been playing great football, and it just goes to show how deadly City are, even when you're two-nil up.
My exact scoreline prediction here is a 2 - 1 win for Palace.
Southampton vs. Chelsea
I think Chelsea's win over the Foxes, was more due to Leicester's incredibly poor form and lack of confidence than anything else. The Blues have been decent, but I'm getting more dubious about the side's chances of getting a position in the top 4 this season.
Southampton just seem completely threatless in my opinion, and I don't fancy them getting a goal in front of their crowd today.
Let's go for a 0 - 2 Chelsea win.
Leeds United vs. Everton
I haven't had the chance to watch much of Leeds and Everton this season, so I won't bore you with a bullshit rant for this one.
Completely on a hunch, I think we'll see a 1 - 1 draw at Elland Road.
Arsenal vs. Aston Villa
I hate to say this, but I think Arsenal have everything in their favor to get 15 points out of 15, with a favorable fixture against a timid Aston Villa.
The Gunners look great on the offensive, and albeit with some distractions at the back-line, they seem as if they're really starting to believe that they can do great things this season.
Lampard is now also one of the most-likely managers to get the sack, and I don't think this game will improve his chances of keeping his job.
Exact scoreline prediction: 2 - 0.
AFC Bournemouth vs. Wolverhampton
Well, I just can't see how Bournemouth can get themselves on the scoresheet. Their confidence must be rock-bottom, and although Wolves haven't been impressive, they do have a way to create danger in the opposition box.
I'm not particularly confident of a Wolves win, but I'd say that a 0 - 1 win for the visitors is in store here.
Manchester City vs. Nottingham Forest
Nothing against Forest (pun intended), but they should brace themselves here.
They were good against Spurs and managed to create tons of chances, albeit with just the one shot on target.
Haaland is going to feast here, and I expect the Norwegian to get add at least two more goals to his tally.
Forecast: 5 - 0 win for City.
West Ham United vs. Tottenham Hotspur
I'm not loving the way that Spurs are playing. They're not exactly in the same shape as at the beginning of last season under Nuno, but they're not far off in my opinion.
They have had some scrappy results, and West Ham is a team that could make things difficult for them. The good thing for Conte's men is that West Ham are not in a great place, and that could end up tipping the scale in this fixture.
This for me is the most unpredictable match of the GW, but I'm going to lean for a 0 - 1 away win at the London Stadium.
Liverpool vs. Newcastle United
Talk about redemption. Liverpool just completely smashed it against Bournemouth at the weekend, and although there's plenty to be excited about, I don't think this will be at all easy for them.
Newcastle are playing some beautiful football and I wouldn't be surprised if they avoided defeat at Anfield; however, my gut is telling me that The Reds will get the three points here with a 2 - 1 win.
Leicester City vs. Manchester United
Leicester are the team you want to play against. They seem completely lost, and their top players (Tielemans and Maddison), look to have their minds set somewhere else.
United weren't great against the Saints, and Ten Hag should be looking to get another dirty win here at the King Power Stadium; I think that there will be a ton of goals here so I'm going for a bold 2 - 3 win for United.
How did we do last week?
Last weekend was pretty predictable, with the lowest Brier Score yet for my model this season. However, when benchmarking it against 538's model, we're still in the dumps – with the model having a 6% higher forecast error.
Leicester has been the team that has been damaging my predictions the most, and I hope my model is quick to learn from their poor performances.
Hope you enjoyed today's issue! Let's see how we fare in this season's fourth gameweek, I'll post the model's error in next week's issue.
If you like my work, please help me by subscribing to my website and sharing my posts.
Catch you later! 👋
